Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 56011
    Prev
    Next
    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Webinar
    -0.08
    reiche
    -0.08
     Smile
    -0.07
    ilator
    -0.07
    рас
    -0.07
    骑
    -0.07
     Twitch
    -0.07
     faite
    -0.07
     quantified
    -0.07
     quar
    -0.07
    POSITIVE LOGITS
     momenten
    0.08
     momentos
    0.08
     toege
    0.08
     pret
    0.08
     moments
    0.08
    ುತ್ತಾರೆ
    0.08
    ುತ್ತದೆ
    0.08
    acency
    0.08
     verschijnen
    0.08
     دف
    0.07
    Activations Density 0.008%

    No Known Activations